Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    on
    -0.07
    aleb
    -0.07
    Connor
    -0.07
    شب
    -0.07
     on
    -0.07
    锥
    -0.07
    expenses
    -0.07
    ependency
    -0.07
     Denmark
    -0.06
    שחר
    -0.06
    POSITIVE LOGITS
     iht
    0.07
    千方百计
    0.07
    �
    0.07
    _unicode
    0.07
     ambigu
    0.07
     شيئا
    0.07
     scarcity
    0.07
     kel
    0.06
    _headers
    0.06
    恹
    0.06
    Act Density 0.011%

    No Known Activations